|
|
 |
| |
|
|
|
Predictive Modeling of Breast Cancer Incidence: A Comparative Study of Fuzzy Time Series and Machine Learning Techniques |
|
|
|
PP: 183-189 |
|
|
|
doi:10.18576/jsap/140204
|
|
|
|
Author(s) |
|
|
|
Ibtisam Daqqa,
Abdullah M. Almarashi,
Mnahil. M. Bashier,
M. Aripov,
Abdelgalal O. I. Abaker,
Azhari A. Alhag,
Alshaikh A. Shokeralla,
|
|
|
|
Abstract |
|
|
| Breast cancer remains a significant public health concern worldwide, prompting researchers to employ a combination of deep learning and statistical models to forecast and classify breast cancer data among women across diverse regions. This methodology facilitates the identification of mortality rate trends associated with breast cancer among females and pinpoints geographical regions with high prevalence rates of the disease. Subsequently, this enables the exploration of potential solutions. This study aims to leverage fuzzy time series and machine learning methodologies for breast cancer data prediction. The primary objective of this research is to conduct a comparative analysis between the multilayer perceptron model and the fuzzy time series model within the framework of breast cancer incidence data. This comparative analysis encompasses a spectrum of accuracy metrics to comprehensively evaluate the performance of both models. Results demonstrate the superiority of the multilayer perceptron model over fuzzy time series model, highlighting its efficacy in breast cancer prediction.
|
|
|
|
|
|
|
|
